Archon
The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
Runssource: GitHubhomepageTypeScriptMITcommit 4d48a0325e64
TypeScript, MIT licensed. The project labels itself: ai, automation, bun, claude, cli, coding assistant, developer tools and typescript.
Archon runs. An Argusic agent installed it in 34 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Bun 1.4.2 installed, 1282 dependencies installed; all 9 workspace packages' tests pass with 0 failures; server starts on port 3090 and serves Archon web UI (HTTP 200); CLI prints full help output; one import-boundary test expectation updated in packages/cli/src/cli.test.ts for bun 1.4.2 compatibility
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- CLI test failure: import boundary expectations stale for bun 1.4.2's code-split chunk grouping3 minutes
- Bun runtime was not installed in the container2 minutes
- Server dev mode crashed with EMFILE from Bun file watcher (container file-descriptor limit)1 minute
- Install time
- 34 minutes
- Cold machine to finish
- 36 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- All 9 package test suites (core 56p, paths 310p, git 236p, isolation 92p, workflows 155p, providers 3p, adapters 2p, web 484p, server 4p) each passed with 0 failures; all 14 CLI test files passed; bun --filter @archon/server start served HTTP 200 at localhost:3090 returning Archon Web UI HTML
- Model tokens used
- 124,801
- Exact commit tested
- 4d48a0325e64
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Start: 07:17 UTC, Now: 07:51 Elapsed minutes: ~34 exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo/packages/cli && timeout 120 bun … exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo/packages/cli && timeout 120 bun … Now I have all the data. Let me produce the final result. 2026-09-22T07:52:43.342263Z ERROR codex_core::session: failed to record rollout items: thread 01a0c… 2026-09-22T07:52:43.342315Z ERROR codex_core::session: failed to record rollout items: thread 01a0c… tokens used 124,801 Now I have all the data. Let me produce the final result.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Took 34 minutes to install, slower than the median of the 36 comparable projects Argusic has measured.
Of the 37 ai projects Argusic has installed and timed, Archon was the 37th fastest to reach a running state, and 30 of 37 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Runs | 100.00 | 0.17 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.17 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.26 |
Topics (from GitHub)
aiautomationbunclaudeclicoding-assistantdeveloper-toolstypescriptworkflow-engineyaml
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/archon)Questions
- Does Archon run?
- Yes. Archon runs. Argusic installed and launched it on a clean machine in 34 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test Archon?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4d48a0325e64. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Archon?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Archon take to install?
- 34 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Archon need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Archon?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Archon compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, Archon was the 37th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for Archon?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.